<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bert-base-uncased-issues-128
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1648
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 16
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1111 | 1.0 | 291 | 1.6933 |
| 1.6349 | 2.0 | 582 | 1.3660 |
| 1.4813 | 3.0 | 873 | 1.4241 |
| 1.3927 | 4.0 | 1164 | 1.4284 |
| 1.3415 | 5.0 | 1455 | 1.2643 |
| 1.2872 | 6.0 | 1746 | 1.3113 |
| 1.2295 | 7.0 | 2037 | 1.2097 |
| 1.2124 | 8.0 | 2328 | 1.2653 |
| 1.179 | 9.0 | 2619 | 1.2648 |
| 1.1486 | 10.0 | 2910 | 1.2159 |
| 1.1268 | 11.0 | 3201 | 1.2639 |
| 1.099 | 12.0 | 3492 | 1.1561 |
| 1.0961 | 13.0 | 3783 | 1.1542 |
| 1.079 | 14.0 | 4074 | 1.0736 |
| 1.0661 | 15.0 | 4365 | 1.2457 |
| 1.0671 | 16.0 | 4656 | 1.1648 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
